What it does
结合chrome-devtools-mcp的能力并加上Skill的规范,实现JSRPC+Flask+autoDecoder方案的前端JS逆向自动化分析,提升JS逆向的效率
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Coding
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/fausto-404-js-reverse-automation-skill)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one js-reverse-automation--skill | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | Fausto-404 | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 615 | 465,460 | 233,910 | 149,364 | 144,149 |
| Last code change | Oct 10, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 17, 2026 |
| License | Apache-2.0 | MIT | – | Apache-2.0 | MIT |
1 skills (instruction sets) by Fausto-404 that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodex
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account Fausto-404 (person), 1 years old
- Use and upkeep
★ 615 stars · code last changed Oct 10, 2026
- Any scripts?
26 scripts that can run on a computer: scripts/JsEnv_Dev.js, scripts/adversarial_diff.py, scripts/ast_candidate_analyzer.js, scripts/build_evidence_graph.py and 22 more
- Uses the internet?
Scripts that go online: scripts/JsEnv_Dev.js, scripts/check_delivery_contract.py, scripts/env_patcher.py, scripts/hook_templates.py
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit d8969b1 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Files are byte-for-byte the same as on GitHub at commit d8969b1 · View on GitHub ↗
26 scripts
Once uploaded it runs on Claude’s systems, not on your computer. No need to unzip
Look inside before downloading
All 45 files · 314 KB
SKILL.md5 KBconstraints/rules.md2 KBreferences/advanced-entrypoints.md16 KBreferences/adversarial-runtime.md3 KBreferences/antidebug-patterns.md22 KBreferences/architecture.md1 KBreferences/browser-session-contract.md3 KBreferences/capability-boundaries.md1 KBreferences/evidence-collection.md12 KBreferences/evolution_matrix.json2 KBreferences/final-report-template.md5 KBreferences/output-contract.md4 KBreferences/security-model.md1 KBschemas/adversarial_trace.schema.json1 KBschemas/analysis_result.schema.json3 KBschemas/candidates.schema.json2 KBschemas/probe_dump.schema.json1 KBscripts/JsEnv_Dev.js4 KBscripts/adversarial_diff.py3 KBscripts/ast_candidate_analyzer.js5 KBscripts/build_evidence_graph.py5 KBscripts/check_delivery_contract.py4 KBscripts/check_inputs.py4 KBscripts/classify_anticrawl.py7 KBscripts/common.py5 KBscripts/detect_encryption.py11 KBscripts/differential_verifier.py8 KBscripts/doctor.py2 KBscripts/emit_adversarial_runtime_probe.py20 KBscripts/emit_burp_doc.py9 KBscripts/emit_flask_proxy.py22 KBscripts/emit_jsrpc_stub.py22 KBscripts/emit_module_probe.py5 KBscripts/emit_runtime_hook_probe.py15 KBscripts/env_patcher.py5 KBscripts/hook_registry.js4 KBscripts/hook_templates.py6 KBscripts/identify_crypto.py3 KBscripts/manage_services.py19 KBscripts/quarantine.py3 KBscripts/source_instrumentor.js6 KBscripts/validate_artifacts.py9 KBscripts/validate_browser_evidence.py6 KBworkflow/pipeline.md8 KBLICENSE11 KB
Download js-reverse-automation.zip
Checking the commands · copy buttons appear once they pass
Open Skills on claude.ai and upload
+Create skillUpload a skillpick js-reverse-automation.zip
No Upload button? Turn on file creation first
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /js-reverse-automation or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /js-reverse-automation or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the js-reverse-automation folder at ~/.agents/skills/js-reverse-automation
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick js-reverse-automation
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick js-reverse-automation
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
2,987 characters · Open the full file on GitHub
---
name: js-reverse-automation
description: 通过 chrome-devtools-mcp 连接真实浏览器,自动定位前端加密入口,生成 JSRPC 注入代码、Flask 代理和 Burp autoDecoder 对接文档。
metadata:
author: Fausto-404
---
# JS 逆向自动化
通过 JSRPC 与真实浏览器完成前端加密入口定位、运行时取证、对抗分析、验证和工程化交付。浏览器连接、文档身份和 action 级结果必须形成可复核证据链。
## 适用场景
- 登录/注册页面密码加密
- API 请求签名
- 表单字段加密
- 响应数据解密
## 输入格式
```
Target URL: https://xxx/login
Parameters To Analyze: password
Optional Fetch Example: fetch("https://xxx/api/login", {...})
```
## 核心流程
1. **预分析 Fetch Example**(如果有)→ 提取加密算法、参数格式、目标 URL
2. 打开页面 → 注入 Hook → 触发目标动作
3. 捕获网络请求 → 定位加密函数
4. 注册 JSRPC → 生成 Flask/Burp 产物
5. 验证输出 → 按标准最终交付格式输出完整结果
遇到反调试、反 Hook、JSVMP、动态 Cookie、环境型签名或动态加载时,先生成并运行 `adversarial_runtime_probe.js`;只有观察到明确对抗信号后,才使用 `--mode intervene` 或源码级插桩。
## 详细工作流
详见 `workflow/pipeline.md`
## 对抗与验证能力
- **对抗运行时探针**:反调试、完整性检查、环境属性、动态代码、响应链、Worker/WebSocket/WASM/iframe 加载事件。
- **持久 Hook**:页面重新赋值后自动检测丢失并尝试恢复;所有 Patch 可通过 `uninstall()` 回滚。
- **Hook 组合**:对抗探针与运行时加密探针共享 `__JSRA_HOOK_REGISTRY__`,同一 API 采用可卸载的分层包装,外部替换只触发一次重建。
- **安全证据**:原始捕获采用有界循环引用安全快照,避免 CryptoJS/JSEncrypt 对象导致导出失败。
- **浏览器会话契约**:注入、调用和导航绑定到当前 tab/document;断线、超时、暂停或导航后不复用旧引用,避免把未知状态误报成成功。
- **控制流观测**:可选观察控制台清理、历史导航、存储访问和关闭页面等干扰信号;只有明确启用干预模式时才阻止受控动作,默认不改变业务行为。
- **源码级保守插桩**:针对明确选择的简单属性读取生成 tap,不默认改写全量代码。
- **对抗差分**:比较基线与干预后的事件、请求、错误和新增证据;差分报告不等于目标已被绕过。
- **完整交付**:标准 JSRPC 产物在调用期间捕获最终 `fetch/XHR` 网络请求,返回明文、最终 route、密文/签名请求体、HTTP 状态和业务响应;最终结果同时保留分析结果、验证表、可复制命令、关闭命令、Burp autoDecoder 配置和生成产物;对抗信息作为补充证据追加。
- **能力边界**:验证码、WebAuthn、设备证明、跨域隔离 Realm 和未导出的 WASM 内部函数仍需保留为人工或 unsupported 路径。
## 交付前强制检查
生成 Flask 代理后必须执行:
```bash
python3 scripts/check_delivery_contract.py \
--proxy generated/flask_proxy.py \
--output artifacts/delivery_contract.json
```
该检查必须同时通过 JSRPC 地址归一化、Burp `application/octet-stream` 完整报文、`Content-Length` 重建和 `dataBody` wrapper 四项回归。`jsrpc.base_url` 可以填写 `http://127.0.0.1:12080` 或 `http://127.0.0.1:12080/go`,生成器必须保证最终只请求一次 `/go`。
端口监听不等于 JSRPC 可用。最终报告前还必须使用真实浏览器执行 action 级 smoke test,并确认返回 `plaintext`、最终 route、非空 `requestBody`、HTTP 状态和业务响应;`/list` 无 action、`/go` 返回 400 或 Flask 返回 502 时,不得写“Flask 代理验证通过”。
将 action 级结果保存后执行:
```bash
python3 scripts/validate_browser_evidence.py \
--input artifacts/jsrpc_smoke.json \
--output artifacts/browser_evidence.json
```
如果同时保存了浏览器桥接状态、`tabId` 和当前 `documentId`,再增加 `--require-session`。超时、断线、待恢复或文档身份变化只能标记为未确认,不能通过重放旧请求来补证据。
Burp 整包模式必须支持外层 `Content-Type: application/octet-stream`,从内层 HTTP 报文识别真实 Content-Type,返回完整改写报文;请求/响应方向仍每次只能选择一个,解密接口和加密接口可以同时配置。
## 约束规则
详见 `constraints/rules.md`
## 参考资料(按需加载)
- 反调试:`references/antidebug-patterns.md`
- 复杂入口:`references/advanced-entrypoints.md`
- 证据收集:`references/evidence-collection.md`
- 能力边界:`references/capability-boundaries.md`
- 输出契约:`references/output-contract.md`
- 最终报告模板:`references/final-report-template.md`
- 对抗运行时:`references/adversarial-runtime.md`
- 浏览器会话与证据:`references/browser-session-contract.md`
## Token 预算
- 单次调用:50,000 token
- 最大工具调用:20 次
- 停止条件:找到入口并验证通过 / 所有降级策略失败 / Token 预算耗尽
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 615
- Maker
- Fausto-404
- License
- Apache-2.0
- Last code change
- Oct 10, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1
- Topics
- ai-tools, automation, burp-suite, javascript, js, js-reverse, reverse, reverse-engineering, security-tools, skills, web-security